Data processing method and device based on graph database, equipment and storage medium

Abstract

The embodiment of the application belongs to the field of artificial intelligence, and relates to a data processing method based on a graph database, comprising the following steps: obtaining call information between a target customer and an agent; obtaining a business node corresponding to a preset standard operation process, and obtaining a business keyword corresponding to the business node; analyzing the call information based on the business keyword, obtaining target attribute information corresponding to the business keyword from the call information, and using the target attribute information as graph data; obtaining customer information of the target customer, and obtaining agent information of the agent; performing data filling on a preset graph database based on the customer information, the agent information and the graph data, to obtain a target graph database; and displaying the target graph database. The application also provides a data processing device based on the graph database, a computer device and a storage medium. In addition, the application also relates to blockchain technology, and the graph data can be stored in the blockchain. The application improves the processing efficiency and intelligence of information mining of the call information.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to data processing methods, apparatus, computer equipment and storage media based on graph databases. Background Technology

[0002] In today's era of advanced internet and big data, effectively utilizing data has become a critical challenge for many internet companies. In sales scenarios, such as insurance product promotion, agents frequently engage in real-time telephone communication with customers, generating a wealth of valuable data within these calls. Currently, there is a lack of rapid and automated data analysis methods for monitoring and analyzing customer-agent call data. It is typically done manually, which is labor-intensive, consumes excessive human and material resources, and fails to quickly and accurately uncover much valuable data hidden within the call data, resulting in low processing efficiency. Summary of the Invention

[0003] The purpose of this application is to propose a data processing method, apparatus, computer equipment, and storage medium based on graph databases to solve the technical problems of existing manual processing methods for monitoring and analyzing customer and agent-related call data, which are labor-intensive, require excessive manpower and resources, and result in the inability to quickly and accurately discover many effective data hidden in the call data, leading to low processing efficiency.

[0004] To address the aforementioned technical problems, this application provides a data processing method based on a graph database, employing the following technical solution:

[0005] Obtain call information between target customers and agents;

[0006] Obtain the business node corresponding to the preset standard operating procedure, and obtain the business keyword corresponding to the business node;

[0007] The call information is analyzed based on the business keywords, and the target attribute information corresponding to the business keywords is obtained from the call information and used as graph data;

[0008] Obtain customer information of the target customer, and obtain seat information of the agent;

[0009] Based on the customer information, the agent information, and the graph data, the preset graph database is populated with data to obtain the target graph database;

[0010] The target graph database is displayed.

[0011] Furthermore, the step of analyzing the call information based on the business keywords, obtaining target attribute information corresponding to the business keywords from the call information, and using it as graph data specifically includes:

[0012] The call information is converted into first text information based on a preset speech recognition model;

[0013] The first text information is filtered based on preset data filtering rules to obtain the target text information;

[0014] Based on a preset mining algorithm, the target text information is analyzed according to the business keywords, and the target attribute information associated with the business keywords is determined from the target text information.

[0015] The target attribute information is used as the graph data.

[0016] Furthermore, the step of filling the preset graph database with data based on the customer information, the agent information, and the graph data to obtain the target graph database specifically includes:

[0017] The customer information is populated into the first person node in the graph database, and the agent information is populated into the second person node in the graph database to obtain the first graph database;

[0018] The graph data is filled into the first attribute filling area corresponding to the first person node in the first graph database to obtain the second graph database;

[0019] Within the second graph database, the edge relationships between the first character node and the second character node are constructed to obtain the target graph database.

[0020] Furthermore, prior to the step of displaying the target graph database, the method further includes:

[0021] The call information is converted into second text information;

[0022] Call the preset analysis model;

[0023] Based on the analysis model, data analysis is performed on the second text information to construct a customer profile of the target customer.

[0024] Fill the customer profile into the first attribute filling area.

[0025] Furthermore, the step of performing data analysis on the second text information based on the analysis model to construct a customer profile of the target customer specifically includes:

[0026] Based on the analysis model, keywords are extracted from the second text information to obtain the first keyword;

[0027] Semantic analysis is performed on the first keyword to obtain the second keyword;

[0028] The customer profile is constructed based on the second keyword.

[0029] Furthermore, prior to the step of displaying the target graph database, the method further includes:

[0030] Obtain the basic attribute information and business information of the agent;

[0031] Based on the basic attribute information and the business information, the agent's profile tags are generated;

[0032] Construct the agent's image based on the image tags;

[0033] Fill the seating image into the second attribute filling area corresponding to the second character node.

[0034] Furthermore, the step of generating the agent's profile tag based on the basic attribute information and the business information specifically includes:

[0035] Feature extraction is performed on the basic attribute information to obtain the corresponding basic attribute labels;

[0036] Feature extraction is performed on the business information to obtain the corresponding business tags;

[0037] The basic attribute tags and the business tags are integrated to obtain the profile tags of the agents.

[0038] To address the aforementioned technical problems, this application also provides a data processing device based on a graph database, employing the following technical solution:

[0039] The first acquisition module is used to acquire call information between the target customer and the agent.

[0040] The second acquisition module is used to acquire the business node corresponding to the preset standard operating procedure and to acquire the business keyword corresponding to the business node.

[0041] The analysis module is used to analyze the call information based on the business keywords, obtain target attribute information corresponding to the business keywords from the call information and use it as graph data;

[0042] The third acquisition module is used to acquire customer information of the target customer and agent information of the agent.

[0043] The first generation module is used to populate a preset graph database with data based on the customer information, the agent information, and the graph data to obtain a target graph database.

[0044] The display module is used to display the target graph database.

[0045] To address the aforementioned technical problems, this application also provides a computer device that employs the following technical solution:

[0046] Obtain call information between target customers and agents;

[0047] Obtain the business node corresponding to the preset standard operating procedure, and obtain the business keyword corresponding to the business node;

[0048] The call information is analyzed based on the business keywords, and the target attribute information corresponding to the business keywords is obtained from the call information and used as graph data;

[0049] Obtain customer information of the target customer, and obtain seat information of the agent;

[0050] Based on the customer information, the agent information, and the graph data, the preset graph database is populated with data to obtain the target graph database;

[0051] The target graph database is displayed.

[0052] To address the aforementioned technical problems, this application also provides a computer-readable storage medium, employing the technical solution described below:

[0053] Obtain call information between target customers and agents;

[0054] Obtain the business node corresponding to the preset standard operating procedure, and obtain the business keyword corresponding to the business node;

[0055] The call information is analyzed based on the business keywords, and the target attribute information corresponding to the business keywords is obtained from the call information and used as graph data;

[0056] Obtain customer information of the target customer, and obtain seat information of the agent;

[0057] Based on the customer information, the agent information, and the graph data, the preset graph database is populated with data to obtain the target graph database;

[0058] The target graph database is displayed.

[0059] Compared with the prior art, the embodiments of this application have the following main advantages:

[0060] This application embodiment obtains call information between a target customer and an agent; obtains business nodes corresponding to a preset standard operating procedure and business keywords corresponding to the business nodes; then analyzes the call information based on the business keywords to extract target attribute information corresponding to the business keywords and use it as graph data; subsequently, it obtains the customer information of the target customer and the agent's agent information; then, it populates a preset graph database with data based on the customer information, the agent information, and the graph data to obtain a target graph database; finally, it displays the target graph database. This application can automatically analyze and quickly extract target attribute information corresponding to business nodes contained in the call information between the target customer and the agent, and use a graph database to store and display the target attribute information in a graph structure to visualize the call information chain, effectively reducing manual workload, realizing the rapid and accurate mining of key information corresponding to business nodes in the call information, and improving the processing efficiency and intelligence of information mining of call information. Attached Figure Description

[0061] To more clearly illustrate the solutions in this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is an exemplary system architecture diagram to which this application can be applied;

[0063] Figure 2 A flowchart of an embodiment of the graph database-based data processing method according to this application;

[0064] Figure 3 This is a schematic diagram of a structure of an embodiment of a graph database-based data processing apparatus according to this application;

[0065] Figure 4 This is a schematic diagram of the structure of one embodiment of the computer device according to this application. Detailed Implementation

[0066] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0067] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0068] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0069] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0070] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0071] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0072] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0073] It should be noted that the data processing method based on graph database provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the data processing device based on graph database is generally located in the server / terminal device.

[0074] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0075] Continue to refer to Figure 2 The diagram illustrates a flowchart of an embodiment of a graph database-based data processing method according to this application. The graph database-based data processing method includes the following steps:

[0076] Step S201: Obtain call information between the target customer and the agent.

[0077] In this embodiment, the data processing method based on the graph database runs on an electronic device (e.g., Figure 1 The server / terminal device shown can acquire call information between the target customer and the agent via wired or wireless connection. It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra-wideband) connections, and other currently known or future-developed wireless connection methods. The aforementioned call information refers to the voice call records between the target customer and the agent.

[0078] Step S202: Obtain the business node corresponding to the preset standard operating procedure, and obtain the business keyword corresponding to the business node.

[0079] In this embodiment, the aforementioned standard operating procedure refers to the process that agents need to perform during telephone communication with customers, which is pre-set according to actual business needs. The standard operating procedure can be understood as the key nodes that agents need to complete in order to complete their telemarketing tasks, such as purchase intention, quotation, insurance selection, insurance discussion, and change of coverage amount.

[0080] Step S203: Analyze the call information based on the business keywords, obtain the target attribute information corresponding to the business keywords from the call information and use it as graph data.

[0081] In this embodiment, the specific implementation process of analyzing the call information based on the business keywords, obtaining target attribute information corresponding to the business keywords from the call information and using it as graph data will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0082] Step S204: Obtain the customer information of the target customer and the seat information of the agent.

[0083] In this embodiment, the customer information of the target customer refers to the customer identification information of the target customer, such as customer 1. The seat information of the agent refers to the seat identification information of the agent, such as agent 1.

[0084] Step S205: Based on the customer information, the agent information, and the graph data, populate the preset graph database with data to obtain the target graph database.

[0085] In this embodiment, the aforementioned graph database can be a Neo4j graph database. The Neo4j graph database stores data in a graph structure. In a graph database, each entity is considered a node, and the relationship between entities is considered an edge. A subgraph of the relationship network is established according to a certain topological relationship, and finally, massive amounts of heterogeneous data from multiple sources are stored through the organization of points and edges. By storing the associated data itself, the relational characteristics of the data can be directly represented. The Neo4j graph database includes labels, nodes, properties, and relationships. For the scenario of visualizing call flow data, labels represent people, and nodes represent individuals with different names, such as customers and agents. Properties can record various detailed data for nodes. Different nodes can be directly explained through relationships, such as agent 1 calling customer 1. Furthermore, the specific implementation process of filling the preset graph database with data based on the customer information, agent information, and graph data to obtain the target graph database will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated upon here.

[0086] Step S206: Display the target graph database.

[0087] In this embodiment, after obtaining the target graph database, it is displayed through the target graph database to visualize the link of call information between the target customer and the agent, so that relevant users can perform business analysis and processing on the agent during the call based on the target graph database, such as identifying bottleneck nodes in the call process.

[0088] This application obtains call information between a target customer and an agent; acquires business nodes corresponding to a preset standard operating procedure and business keywords corresponding to those business nodes; then analyzes the call information based on the business keywords to extract target attribute information corresponding to the business keywords and uses it as graph data; subsequently, it acquires the target customer's customer information and the agent's agent information; then, it populates a preset graph database with the customer information, agent information, and graph data to obtain a target graph database; finally, it displays the target graph database. This application can automatically analyze and quickly extract target attribute information corresponding to business nodes contained in the call information between the target customer and the agent, and uses a graph database to store and display this target attribute information in a graph structure to visualize the call information chain, effectively reducing manual workload, achieving rapid and accurate mining of key information corresponding to business nodes in the call information, and improving the processing efficiency and intelligence of call information mining.

[0089] In some alternative implementations, step S203 includes the following steps:

[0090] The call information is converted into first text information based on a preset speech recognition model.

[0091] In this embodiment, the speech recognition model is used to convert speech information into text content. The speech recognition model is used to obtain the spectral features of the call information, and the spectral features of the call information are matched with the physical spectral features corresponding to vowels, syllables or words that are pre-stored in the speech recognition model. The text corresponding to the physical spectral features that are the same as the spectral features of the call information is output, thereby converting the call information into the corresponding text file, namely the first text information.

[0092] The first text information is filtered based on preset data filtering rules to obtain the target text information.

[0093] In this embodiment, the aforementioned data filtering rules refer to rules pre-set by business personnel for filtering call information. Specifically, filtering algorithms can be used to filter useless information in the call information, such as filtering information unrelated to business. The aforementioned target text information refers to the text information consisting of the remaining call data after filtering the data in the first text information.

[0094] Based on a preset mining algorithm, the target text information is analyzed according to the business keywords, and the target attribute information associated with the business keywords is determined from the target text information.

[0095] In this embodiment, the aforementioned mining algorithm can specifically be a decision tree data mining algorithm. A decision tree is a decision analysis method that, based on known probabilities of various scenarios, constructs a decision tree to calculate the probability that the expected net present value is greater than or equal to zero, evaluating project risk and determining project feasibility. It is a graphical method that intuitively applies probability analysis. Specifically, after obtaining the target text information and the business keywords corresponding to the business nodes of the standard operating procedure, the decision tree data mining algorithm can be used to analyze the target text information based on the business keywords to determine the target attribute information associated with the business keywords. For example, the aforementioned business keywords may include purchase intention, price quote, and risk selection. The mining algorithm can then extract the purchase intention results, price quote results, and risk selection results of target users respectively associated with purchase intention, price quote, and risk selection from the target text information, and use these as target attribute information.

[0096] The target attribute information is used as the graph data.

[0097] This application uses speech recognition models, data filtering rules, and mining algorithms to process calls, which can quickly and accurately generate graph data associated with business keywords corresponding to business nodes. This is beneficial for subsequent processing of preset graph data based on this graph data to construct a target graph database.

[0098] In some optional implementations of this embodiment, step S205 includes the following steps:

[0099] The customer information is populated into the first person node in the graph database, and the agent information is populated into the second person node in the graph database to obtain the first graph database.

[0100] In this embodiment, a first person node and a second person node are pre-set in the graph database. By filling customer information into the first person node in the graph database, a relationship between the target customer and the first person node is established; by filling agent information into the second person node in the graph database, a relationship between the agent and the second person node is established.

[0101] The graph data is filled into the first attribute filling area corresponding to the first person node in the first graph database to obtain the second graph database.

[0102] In this embodiment, the graph database is further provided with a first attribute filling area corresponding to the first person node. By filling the first attribute filling area corresponding to the first person node in the first graph database with the graph data corresponding to the target customer, the call details information of the target customer, i.e. the above-mentioned graph data, is recorded in the first attribute filling area, so as to realize the use of graph data to record and track the communication between the target customer and the agent.

[0103] Within the second graph database, the edge relationships between the first character node and the second character node are constructed to obtain the target graph database.

[0104] In this embodiment, the edge relationship between the first person node and the second person node may include: the agent made a phone call to the target customer.

[0105] This application obtains a target graph database by filling customer information and agent information into first and second person nodes in a graph data, respectively, filling the graph database with the attribute filling area corresponding to the first person node associated with the customer information, and constructing edge relationships between the first and second person nodes within the graph database. This allows for visualization of the call information link between the target customer and the agent. By using graph data to record and track the communication between the target customer and the agent, relevant users can perform business analysis on the agent during the call based on the target graph database, thereby quickly and accurately identifying bottleneck nodes in the call process.

[0106] In some alternative implementations, prior to step S206, the electronic device may also perform the following steps:

[0107] The call information is converted into second text information.

[0108] In this embodiment, the above-described speech recognition model can be used to convert the call information into second text information. The generation process of the second text information can refer to the generation process of the first text information, and will not be elaborated further here.

[0109] Call the preset analysis model.

[0110] In this embodiment, the above-mentioned analysis model is a model used for semantic analysis of words or sentences. The analysis model can be a Chinese semantic analysis system such as bosonnlp, or a natural language processing tool such as FudanNLP. The specific model can be set according to actual usage needs and is not limited here.

[0111] Based on the analysis model, the second text information is analyzed to construct a customer profile of the target customer.

[0112] In this embodiment, semantic analysis can be performed on the second text information using an analysis model to understand the meaning, theme, and similarity of words and sentences in the second text information. Based on the associations existing in the words, sentences, and text, relevant semantic information can be identified, thus obtaining the semantic analysis results and the user characteristics of the target user. These user characteristics refer to the target user's interests, hobbies, and behavioral habits, which can then be used as a customer profile for the target customer.

[0113] Fill the customer profile into the first attribute filling area.

[0114] In this embodiment, by filling the customer profile into the first attribute filling area corresponding to the first person node, relevant users can easily and clearly view the profile information of the target customer.

[0115] This application uses an analytical model to analyze and process call information, thereby quickly building customer profiles of target customers and filling these profiles into the first attribute filling area of ​​the target graph database. In other words, by using the target graph database to synchronously record customer profiles of target customers, agents can better understand the needs of target customers and improve their user experience.

[0116] In some optional implementations, the above-mentioned data analysis of the second text information based on the analysis model to construct the customer profile of the target customer includes the following steps:

[0117] Based on the analysis model, keywords are extracted from the second text information to obtain the first keyword.

[0118] In this embodiment, by using an analysis model to analyze and process the statements in the second text information, words that can reflect the theme or main content of the second text information are extracted as keywords to obtain the aforementioned first keyword.

[0119] Semantic analysis of the first keyword yields the second keyword.

[0120] In this embodiment, after obtaining the first keyword, the semantic analysis of the first keyword is performed using an analysis model to understand the semantic information such as the meaning, theme and similarity expressed by the first keyword, and the relevant semantic information is identified based on the association information existing in the keyword. The keywords are then concatenated based on the results of the semantic analysis, or the keywords are mapped to the user's behavioral habits or interests using a fuzzy query method in the corpus of the analysis model to obtain the second keyword.

[0121] The customer profile is constructed based on the second keyword.

[0122] In this embodiment, by integrating all the second keywords, an integrated word set is obtained, and this word set is then used as the customer profile of the target customer to complete the construction of the customer profile.

[0123] This application uses an analytical model to extract keywords and perform semantic analysis on the second text information corresponding to the call information to obtain the corresponding keywords. Based on these keywords, a customer profile of the target customer can be quickly constructed, ensuring the accuracy and generation speed of the customer profile.

[0124] In some optional implementations of this embodiment, before step S206, the electronic device may further perform the following steps:

[0125] Obtain the basic attribute information and business information of the agent.

[0126] In this embodiment, the basic attribute information may include the agent's name, age, gender, etc. Business information corresponding to the agent can be retrieved from a preset agent information database. This business information may include the agent's service area information and the weights of various service areas. For example, the service area information may include: life insurance, property insurance, and auto insurance, with life insurance having a weight of 0.5, property insurance having a weight of 0.3, and auto insurance having a weight of 0.2.

[0127] The agent's profile tag is generated based on the basic attribute information and the business information.

[0128] In this embodiment, the specific implementation process of generating the agent's profile label based on the basic attribute information and the business information will be further described in detail in subsequent specific embodiments of this application, and will not be elaborated on here.

[0129] The agent's portrait is constructed based on the portrait tags.

[0130] In this embodiment, user profiling is essentially a mathematical model that abstracts various specific attributes and behaviors of users in the real world. It involves integrating and processing user-related data to form tag data that can be used for modeling, and then constructing the corresponding profile using appropriate algorithms or models. Specifically, the agent profile to be constructed is a profile model, and the agent's profile tags are symbols used to express this profile model. The profile tags represent a partial-to-whole correspondence with the profile; therefore, by integrating all the agent's profile tags, the agent's profile can be obtained.

[0131] Fill the seating image into the second attribute filling area corresponding to the second character node.

[0132] In this embodiment, by filling the image of the agent into the second attribute filling area corresponding to the second person node, the relevant user can clearly view the image information of the agent.

[0133] This application achieves rapid construction of agent profiles by analyzing and processing the basic attribute information and business information of the acquired agents, and then fills the second attribute filling area of ​​the target graph database with the agent profiles. In other words, by using the target graph database to synchronously record the agent profiles, relevant users can better understand the agent's profile information, and then combine the agent profiles to analyze and match customers who are suitable for the agent, thereby improving the user experience.

[0134] In some optional implementations of this embodiment, generating the agent's profile tag based on the basic attribute information and the business information includes the following steps:

[0135] Feature extraction is performed on the basic attribute information to obtain the corresponding basic attribute labels.

[0136] In this embodiment, the basic attribute information of the agent can be statistically analyzed and features extracted to form the agent's basic attribute label. After extracting the corresponding first feature from the basic attribute information, the agent's basic attribute label can be constructed based on the first feature. For example, if the agent's basic attribute information is male between 20 and 30 years old, then for males aged 20 to 30, the basic attribute label "young man" can be formed by extracting age group and gender features.

[0137] Feature extraction is performed on the business information to obtain the corresponding business tags.

[0138] In this embodiment, after extracting the corresponding second feature from the business information, a business tag for the agent can be constructed based on the second feature. For example, suppose the above business information includes: life insurance, property insurance, and auto insurance, etc., with the life insurance service area having a weight of 0.5, the property insurance service area having a weight of 0.3, and the auto insurance service area having a weight of 0.2. Then, by extracting the service area name and weight feature from the business information, business tags such as "life insurance (0.5)", "property insurance (0.3)", and "auto insurance (0.2)" can be formed.

[0139] The basic attribute tags and the business tags are integrated to obtain the profile tags of the agents.

[0140] In this embodiment, an integrated tag is obtained by integrating basic attribute tags and business tags, and this integrated tag is used as the profile tag of the agent.

[0141] This application extracts features from basic attribute information and business information to obtain corresponding basic attribute tags and business tags, and then integrates these basic attribute tags and business tags to quickly generate agent profile tags. This is beneficial for quickly and accurately constructing agent profiles based on these profile tags, thereby improving the accuracy and generation speed of agent profile construction.

[0142] It should be emphasized that, to further ensure the privacy and security of the graph data, the graph data can also be stored in a node of a blockchain.

[0143] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0144] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0145] Foundational technologies for artificial intelligence generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interactive systems, and mechatronics. AI software technologies mainly encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0146] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a computer-readable storage medium. When executed, the program can include the processes of the embodiments of the above methods. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0147] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0148] Further reference Figure 3 As a response to the above Figure 2 The implementation of the method shown in this application provides an embodiment of a data processing device based on a graph database, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0149] like Figure 3 As shown, the data processing device 300 based on a graph database described in this embodiment includes: a first acquisition module 301, a second acquisition module 302, an analysis module 303, a third acquisition module 304, a first generation module 305, and a display module 306. Wherein:

[0150] The first acquisition module 301 is used to acquire call information between the target customer and the agent;

[0151] The second acquisition module 302 is used to acquire the business node corresponding to the preset standard operating procedure and to acquire the business keyword corresponding to the business node;

[0152] Analysis module 303 is used to analyze the call information based on the business keywords, obtain target attribute information corresponding to the business keywords from the call information and use it as graph data;

[0153] The third acquisition module 304 is used to acquire customer information of the target customer and to acquire seat information of the agent.

[0154] The first generation module 305 is used to fill a preset graph database with data based on the customer information, the agent information, and the graph data to obtain a target graph database.

[0155] Display module 306 is used to display the target graph database.

[0156] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0157] In some optional implementations of this embodiment, the analysis module 303 includes:

[0158] The conversion submodule is used to convert the call information into first text information based on a preset speech recognition model;

[0159] The filtering submodule is used to filter the first text information based on preset data filtering rules to obtain the target text information.

[0160] The first analysis submodule is used to perform data analysis on the target text information based on the business keywords according to a preset mining algorithm, and to determine the target attribute information associated with the business keywords from the target text information;

[0161] The determination submodule is used to use the target attribute information as the graph data.

[0162] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0163] In some optional implementations of this embodiment, the first generation module 305 includes:

[0164] The first filling submodule is used to fill the customer information into the first person node in the graph database, and to fill the agent information into the second person node in the graph database, to obtain the first graph database;

[0165] The second filling submodule is used to fill the graph data into the first attribute filling area corresponding to the first person node in the first graph database to obtain the second graph database.

[0166] The first generation submodule is used to construct the edge relationship between the first character node and the second character node in the second graph database to obtain the target graph database.

[0167] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the graph database-based data processing method in the aforementioned implementation method, and will not be repeated here.

[0168] In some optional implementations of this embodiment, the data processing apparatus based on the graph database further includes:

[0169] The conversion module is used to convert the call information into second text information;

[0170] The calling module is used to invoke a preset analysis model;

[0171] The second generation module is used to perform data analysis on the second text information based on the analysis model to construct a customer profile of the target customer.

[0172] The first filling module is used to fill the customer profile into the first attribute filling area.

[0173] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0174] In some optional implementations of this embodiment, the second generation module includes:

[0175] The first extraction submodule is used to extract keywords from the second text information based on the analysis model to obtain the first keyword;

[0176] The second analysis submodule is used to perform semantic analysis on the first keyword to obtain the second keyword;

[0177] A submodule is constructed to build the customer profile based on the second keyword.

[0178] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0179] In some optional implementations of this embodiment, the data processing apparatus based on the graph database further includes:

[0180] The fourth acquisition module is used to acquire the basic attribute information and business information of the agent;

[0181] The third generation module is used to generate profile tags for the agents based on the basic attribute information and the business information;

[0182] A construction module is used to construct the agent's image based on the image tags;

[0183] The second filling module is used to fill the seat image into the second attribute filling area corresponding to the second person node.

[0184] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0185] In some optional implementations of this embodiment, the third generation module includes:

[0186] The second extraction submodule is used to extract features from the basic attribute information to obtain the corresponding basic attribute labels;

[0187] The third extraction submodule is used to extract features from the business information to obtain corresponding business tags;

[0188] The second generation submodule is used to integrate the basic attribute tags and the business tags to obtain the agent's profile tags.

[0189] In this embodiment, the operations performed by the above modules or units correspond one-to-one with the steps of the data processing method based on graph database in the aforementioned implementation method, and will not be repeated here.

[0190] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0191] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components 41-43 is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0192] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0193] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for graph database-based data processing methods. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0194] In some embodiments, the processor 42 may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions stored in the memory 41 or to process data, for example, to execute computer-readable instructions of the graph database-based data processing method.

[0195] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0196] Compared with the prior art, the embodiments of this application have the following main advantages:

[0197] In this embodiment, the process involves acquiring call information between a target customer and an agent; acquiring business nodes corresponding to a preset standard operating procedure and business keywords corresponding to those business nodes; analyzing the call information based on the business keywords to extract target attribute information corresponding to those keywords and using it as graph data; acquiring the target customer's customer information and the agent's agent information; subsequently, filling a preset graph database with data based on the customer information, agent information, and graph data to obtain a target graph database; and finally displaying the target graph database. This application enables automatic analysis and rapid extraction of target attribute information corresponding to business nodes contained in the call information between the target customer and the agent, and uses a graph database to store and display this target attribute information in a graph structure, thus visualizing the call information chain. This effectively reduces manual workload, achieves rapid and accurate extraction of key information corresponding to business nodes in the call information, and improves the processing efficiency and intelligence of call information mining.

[0198] This application also provides another embodiment, namely, providing a computer-readable storage medium storing computer-readable instructions that can be executed by at least one processor to cause the at least one processor to perform the steps of the graph database-based data processing method described above.

[0199] Compared with the prior art, the embodiments of this application have the following main advantages:

[0200] In this embodiment, the process involves acquiring call information between a target customer and an agent; acquiring business nodes corresponding to a preset standard operating procedure and business keywords corresponding to those business nodes; analyzing the call information based on the business keywords to extract target attribute information corresponding to those keywords and using it as graph data; acquiring the target customer's customer information and the agent's agent information; subsequently, filling a preset graph database with data based on the customer information, agent information, and graph data to obtain a target graph database; and finally displaying the target graph database. This application enables automatic analysis and rapid extraction of target attribute information corresponding to business nodes contained in the call information between the target customer and the agent, and uses a graph database to store and display this target attribute information in a graph structure, thus visualizing the call information chain. This effectively reduces manual workload, achieves rapid and accurate extraction of key information corresponding to business nodes in the call information, and improves the processing efficiency and intelligence of call information mining.

[0201] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0202] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A data processing method based on graph databases, characterized in that, Includes the following steps: Obtain call information between target customers and agents; Obtain the business node corresponding to the preset standard operating procedure, and obtain the business keyword corresponding to the business node; The call information is analyzed based on the business keywords, and the target attribute information corresponding to the business keywords is obtained from the call information and used as graph data; Obtain customer information of the target customer, and obtain seat information of the agent; Based on the customer information, the agent information, and the graph data, the preset graph database is populated with data to obtain the target graph database; The target graph database is displayed.

2. The data processing method based on graph database according to claim 1, characterized in that, The step of analyzing the call information based on the business keywords, obtaining target attribute information corresponding to the business keywords from the call information, and using it as graph data specifically includes: The call information is converted into first text information based on a preset speech recognition model; The first text information is filtered based on preset data filtering rules to obtain the target text information; Based on a preset mining algorithm, the target text information is analyzed according to the business keywords, and the target attribute information associated with the business keywords is determined from the target text information. The target attribute information is used as the graph data.

3. The data processing method based on graph database according to claim 1, characterized in that, The step of filling a preset graph database with data based on the customer information, the agent information, and the graph data to obtain the target graph database specifically includes: The customer information is populated into the first person node in the graph database, and the agent information is populated into the second person node in the graph database to obtain the first graph database; The graph data is filled into the first attribute filling area corresponding to the first person node in the first graph database to obtain the second graph database; Within the second graph database, the edge relationships between the first character node and the second character node are constructed to obtain the target graph database.

4. The data processing method based on graph database according to claim 3, characterized in that, Prior to the step of displaying the target graph database, the method further includes: The call information is converted into second text information; Call the preset analysis model; Based on the analysis model, data analysis is performed on the second text information to construct a customer profile of the target customer. Fill the customer profile into the first attribute filling area.

5. The data processing method based on graph database according to claim 4, characterized in that, The step of performing data analysis on the second text information based on the analysis model to construct a customer profile of the target customer specifically includes: Based on the analysis model, keywords are extracted from the second text information to obtain the first keyword; Semantic analysis is performed on the first keyword to obtain the second keyword; The customer profile is constructed based on the second keyword.

6. The data processing method based on graph database according to claim 3, characterized in that, Prior to the step of displaying the target graph database, the method further includes: Obtain the basic attribute information and business information of the agent; Based on the basic attribute information and the business information, the agent's profile tags are generated; Construct the agent's image based on the image tags; Fill the seating image into the second attribute filling area corresponding to the second character node.

7. The data processing method based on graph database according to claim 6, characterized in that, The step of generating the agent's profile tag based on the basic attribute information and the business information specifically includes: Feature extraction is performed on the basic attribute information to obtain the corresponding basic attribute labels; Feature extraction is performed on the business information to obtain the corresponding business tags; The basic attribute tags and the business tags are integrated to obtain the profile tags of the agents.

8. A data processing device based on a graph database, characterized in that, include: The first acquisition module is used to acquire call information between the target customer and the agent. The second acquisition module is used to acquire the business node corresponding to the preset standard operating procedure and to acquire the business keyword corresponding to the business node. The analysis module is used to analyze the call information based on the business keywords, obtain target attribute information corresponding to the business keywords from the call information and use it as graph data; The third acquisition module is used to acquire customer information of the target customer and agent information of the agent. The first generation module is used to populate a preset graph database with data based on the customer information, the agent information, and the graph data to obtain a target graph database. The display module is used to display the target graph database.

9. A computer device comprising a memory and a processor, the memory storing computer-readable instructions, wherein the processor, when executing the computer-readable instructions, implements the steps of the data processing method based on a graph database as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the data processing method based on a graph database as described in any one of claims 1 to 7.

Images